End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: tiny_bert_rand_100_v1_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5633802816901409
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_100_v1_wnli
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v1](https://huggingface.co/Hartunka/tiny_bert_rand_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v1](https://huggingface.co/Hartunka/tiny_bert_rand_100_v1) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7075
-- Accuracy: 0.3521
+- Loss: 0.6914
+- Accuracy: 0.5634
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.69140625,
+    "eval_runtime": 0.0594,
+    "eval_samples": 71,
+    "eval_samples_per_second": 1196.029,
+    "eval_steps_per_second": 16.845,
+    "total_flos": 99911832606720.0,
+    "train_loss": 0.6944943798912896,
+    "train_runtime": 7.0819,
+    "train_samples": 635,
+    "train_samples_per_second": 4483.276,
+    "train_steps_per_second": 21.181
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.69140625,
+    "eval_runtime": 0.0594,
+    "eval_samples": 71,
+    "eval_samples_per_second": 1196.029,
+    "eval_steps_per_second": 16.845
+}

logs/events.out.tfevents.1744833280.s_004_m

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11143d132dbc9ce460025fc3d51996919d310ead4de58b83ab4b15441a0fcb9
+size 308

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 99911832606720.0,
+    "train_loss": 0.6944943798912896,
+    "train_runtime": 7.0819,
+    "train_samples": 635,
+    "train_samples_per_second": 4483.276,
+    "train_steps_per_second": 21.181
+}

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.69140625,
+  "best_model_checkpoint": "tiny_bert_rand_100_v1_wnli/checkpoint-3",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5936211347579956,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6941,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.69140625,
+      "eval_runtime": 0.0465,
+      "eval_samples_per_second": 1527.008,
+      "eval_steps_per_second": 21.507,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4567447602748871,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6962,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6954226493835449,
+      "eval_runtime": 0.0398,
+      "eval_samples_per_second": 1783.41,
+      "eval_steps_per_second": 25.118,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.458055317401886,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6966,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.7034552097320557,
+      "eval_runtime": 0.0365,
+      "eval_samples_per_second": 1943.835,
+      "eval_steps_per_second": 27.378,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6440699100494385,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6913,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4084507042253521,
+      "eval_loss": 0.6997138857841492,
+      "eval_runtime": 0.0352,
+      "eval_samples_per_second": 2018.447,
+      "eval_steps_per_second": 28.429,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8741340041160583,
+      "learning_rate": 4.5e-05,
+      "loss": 0.696,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4507042253521127,
+      "eval_loss": 0.700704038143158,
+      "eval_runtime": 0.0371,
+      "eval_samples_per_second": 1913.976,
+      "eval_steps_per_second": 26.957,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.6335508227348328,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6928,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.352112676056338,
+      "eval_loss": 0.7075263857841492,
+      "eval_runtime": 0.0356,
+      "eval_samples_per_second": 1995.882,
+      "eval_steps_per_second": 28.111,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "step": 18,
+      "total_flos": 99911832606720.0,
+      "train_loss": 0.6944943798912896,
+      "train_runtime": 7.0819,
+      "train_samples_per_second": 4483.276,
+      "train_steps_per_second": 21.181
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 99911832606720.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}